Non-linear satellite state modeling techniques

Abstract

Techniques are provided for non-linear satellite state modeling. First global navigation satellite systems (GNSS) signal data is obtained from a set of GNSS satellites. First satellite state data is obtained. The first satellite state data includes orbit data for the set of GNSS satellites. A non-linear satellite state model that includes a plurality of model parameters is generated. The non-linear satellite state model is generated by adjusting the plurality of model parameters based on the first GNSS signal data and the first satellite state data. The non-linear satellite state model outputs satellite state data based on GNSS signal data. Second GNSS signal data is obtained from the set of GNSS satellites. A set of updated satellite state data is calculated using the non-linear satellite state model and the second GNSS signal data.

What is claimed is: 
     
       1. A computer system comprising:
 one or more hardware processors; 
 at least one memory coupled to the one or more hardware processors and storing one or more instructions which, when executed by the one or more hardware processors, cause the one or more hardware processors to:
 obtain first global navigation satellite systems (GNSS) signal data from a set of GNSS satellites; 
 obtain first satellite state data generated by a model, the first satellite state data comprising estimated orbit data valid at one or more particular times for the set of GNSS satellites; 
 generate a non-linear satellite state model comprising a plurality of model parameters by adjusting the plurality of model parameters using one or more machine learning techniques based on the first GNSS signal data and the first satellite state data, wherein the non-linear satellite state model generates output satellite state data based on GNSS signal data; 
 obtain second GNSS signal data from the set of GNSS satellites; and 
 for a particular GNSS satellite of the set of GNSS satellites, calculate updated satellite state data for use by the particular GNSS satellite, the updated satellite state data comprising one or more updated values describing the particular GNSS satellite's orbit data using the non-linear satellite state model and the second GNSS signal data. 
 
 
     
     
       2. The computer system of  claim 1 , wherein the non-linear satellite state model comprises an artificial neural network, wherein the plurality of model parameters comprise a plurality of weights of the artificial neural network. 
     
     
       3. The computer system of  claim 1 , wherein the first satellite state data is generated by a GNSS ground infrastructure system. 
     
     
       4. The computer system of  claim 3 , wherein the first satellite state data is obtained from the set of GNSS satellites. 
     
     
       5. The computer system of  claim 1 , wherein the one or more instructions, when executed by the one or more hardware processors, cause the one or more hardware processors to:
 provide the updated satellite state data for uploading to the GNSS satellites using one or more transmitters. 
 
     
     
       6. The computer system of  claim 5 , wherein providing the updated satellite state data for uploading to the GNSS satellites using one or more transmitters comprises providing the updated satellite state data to a GNSS ground infrastructure system. 
     
     
       7. The computer system of  claim 1 ,
 wherein the first satellite state data includes a set of one or more clock error parameters for at least one GNSS satellite of the set of GNSS satellites, and 
 wherein the updated satellite data includes one or more clock error parameters for the particular GNSS satellite. 
 
     
     
       8. The computer system of  claim 1 , wherein the satellite state data includes a set of one or more orbit parameters for at least one GNSS satellite of the GNSS satellites. 
     
     
       9. The computer system of  claim 1 , wherein the one or more instructions, when executed by the one or more hardware processors, cause the one or more hardware processors to:
 cause transmission of the updated satellite state data to the particular GNSS satellite. 
 
     
     
       10. The computer system of  claim 1 , wherein the one or more instructions, when executed by the one or more hardware processors, cause the one or more hardware processors to:
 for one or more additional GNSS satellites of the set of GNSS satellites, calculate additional updated satellite state data for use by the one or more additional GNSS satellites, the additional updated satellite state data comprising one or more updated values describing the one or more additional GNSS satellites' orbit data using the non-linear satellite state model and the second GNSS signal data. 
 
     
     
       11. The computer system of  claim 1 , wherein the model is a linear model that estimates the first satellite state data. 
     
     
       12. A method comprising:
 obtaining first global navigation satellite systems (GNSS) signal data from a set of GNSS satellites; 
 obtaining first satellite state data generated by a model, the first satellite state data comprising estimated orbit data valid at one or more particular times for the set of GNSS satellites; 
 generating a non-linear satellite state model comprising a plurality of model parameters by adjusting the plurality of model parameters using one or more machine learning techniques based on the GNSS signal data and the satellite state data, wherein the non-linear satellite state model generates output satellite state data based on GNSS signal data; 
 obtaining second GNSS signal data from the set of GNSS satellites; and 
 for a particular GNSS satellite of the set of GNSS satellites, calculating updated satellite state data for use by the particular GNSS satellite, the updated satellite state data comprising one or more updated values describing the particular GNSS satellite's orbit data using the non-linear satellite state model and the second GNSS signal data; 
 wherein the method is performed by one or more computing devices. 
 
     
     
       13. The method of  claim 12 , wherein the non-linear satellite state model comprises an artificial neural network, wherein the plurality of model parameters comprise a plurality of weights of the artificial neural network. 
     
     
       14. The method of  claim 12 , wherein the first satellite state data is generated by a GNSS ground infrastructure system. 
     
     
       15. The method of  claim 14 , wherein the first satellite state data is obtained from the set of GNSS satellites. 
     
     
       16. The method of  claim 12 , further comprising:
 providing the updated satellite state data for uploading to the GNSS satellites using one or more transmitters. 
 
     
     
       17. The method of  claim 16 , wherein providing the updated satellite state data for uploading to the GNSS satellites using one or more transmitters comprises providing the updated satellite state data to a GNSS ground infrastructure system. 
     
     
       18. The method of  claim 8 ,
 wherein the first satellite state data includes a set of one or more clock error parameters for at least one GNSS satellite of the set of GNSS satellites; and 
 wherein the updated satellite state data includes one or more clock error parameters for the particular GNSS satellite. 
 
     
     
       19. The method of  claim 12 , wherein the satellite state data includes a set of one or more orbit parameters for at least one GNSS satellite of the GNSS satellites. 
     
     
       20. The method of  claim 12 , wherein the model is a linear model that estimates the first satellite state data.